Techniques for Enhancing Multiple View Performance in a Three Dimensional Pipeline

1. An article of manufacture comprising a non-transitory storage medium containing instructions that when executed cause a system to: receive a plurality of view transformations, each view transformation of the plurality of view transformations to be associated with a respective view among a plurality of views of a three dimensional image; compile vertex data associated with the image; and determine, by performing the plurality of view transformations on the compiled vertex data through a single run of a vertex pipeline, separate operation data for each view of the plurality of views.

2. The article of manufacture of claim 1 , the non-transitory storage medium containing instructions that when executed cause the system to receive the vertex data associated with the image.

3. The article of manufacture of claim 1 , the non-transitory storage medium containing instructions that when executed cause the system to render the operation data for each view of the plurality of views sequentially according to an interval period.

4. The article of manufacture of claim 1 , the non-transitory storage medium containing instructions that when executed cause the system to store the operation data for each view of the plurality of views in one or more buffers.

5. The article of manufacture of claim 1 , the non-transitory storage medium containing instructions that when executed cause the system to: clip the operation data for at least one view of the plurality of views; and tile the clipped operation data for the at least one view.

6. The article of manufacture of claim 1 , the non-transitory storage medium containing instructions that when executed cause the system to allocate multiple input spaces within a tiling processor, each input space of the multiple input spaces to store the operation data for at least one view of the plurality of views.

7. The article of manufacture of claim 1 , the non-transitory storage medium containing instructions that when executed cause the system to allocate multiple output spaces within a shader processor, each output space of the multiple output spaces to store the operation data for at least one view of the plurality of views.

8. A method, comprising: receiving at a graphics processing unit a plurality of view transformations, each view transformation of the plurality of view transformations to be associated with a respective view among a plurality of views of a three dimensional image; compiling vertex data associated with the image; determining, by performing the plurality of view transformations on the compiled vertex data through a single run of a vertex pipeline, separate operation data for each view of the plurality of views; and storing the operation data for the plurality of views within memory coupled to the graphics processing unit.

9. The method of claim 8 , comprising: receiving at the graphics processing unit the vertex data associated with the image.

10. The method of claim 8 , comprising: rendering the operation data for each view of the plurality of views sequentially according to an interval period.

11. The method of claim 8 , comprising: storing within the memory the operation data for each view of the plurality of views in one or more buffers.

12. The method of claim 8 , comprising: clipping the operation data for at least one view of the plurality of views; and tiling the clipped operation data for the at least one view.

13. The method of claim 8 , comprising: allocating multiple input spaces within a tiling processor of the graphics processing unit, each input space of the multiple input spaces to store the operation data for at least one view of the plurality of views.

14. The method of claim 8 , comprising: allocating multiple output spaces within a shader processor of the graphics processing unit, each output space of the multiple output spaces to store the operation data for at least one view of the plurality of views.

15. An apparatus comprising: a graphics processing unit comprising: a three dimensional driver with a vertex component operative to: receive a plurality of view transformations, each view transformation of the plurality of view transformations to be associated with a respective view among a plurality of views of a three dimensional image; compile vertex data for the image; and determine, by performing the plurality of view transformations on the compiled vertex data through a single run of a vertex pipeline, separate operation data for each view of the plurality of views.

16. The apparatus of claim 15 , the vertex component comprising: a memory controller component operative to: allocate multiple output spaces within a shader processor; and the shader processor to: receive the compiled vertex data, and place the operation data for the plurality of views in the multiple output spaces, each output space of the multiple output spaces to store the operation data for a respective view of the plurality of views, and the operation data for each view of the plurality of views associated with a respective view transformation of the plurality of view transformations.

17. The apparatus of claim 15 , the graphics processing unit comprising: an application program interface operative to receive the plurality of view transformations to render an image.

18. The apparatus of claim 15 , the graphics processing unit comprising: an application program interface operative to receive an interval period between each rendering of the operation data for one of the views of the plurality of views.

19. The apparatus of claim 15 , the graphics processing unit comprising: an application program interface operative to determine whether a view transforming application is enabled.

20. The apparatus of claim 15 , the vertex component comprising: a memory controller operative to allocate multiple input spaces within a tiling processor; and the tiling processor to: receive the operation data for at least one view of the plurality of views; clip the operation data for the at least one view; and tile the operation data for the at least one view.

21. The apparatus of claim 15 , the three dimensional driver comprising: a pixel component operative to render the operation data for each view of the plurality of views sequentially according to an interval period.

22. The apparatus of claim 15 , the three dimensional driver comprising: one or more buffers to store the operation data for each view of the plurality of views.

23. The apparatus of claim 15 , comprising: a digital display communicatively coupled to the graphics processing unit, the digital display operative to present the plurality of views of the image.

24. A system, comprising: a processing unit to execute a three dimensional driver; a display accessible to the processing unit; a memory unit coupled to the processing unit to store the three dimensional driver, the three dimensional driver to cause the processing unit to: receive at the processing unit a plurality of view transformations, each view transformation of the plurality of view transformations to be associated with a respective view among a plurality of views of a three dimensional image; receive at the processing unit vertex data for the image; compile the vertex data; determine, by performing the plurality of view transformations on the compiled vertex data through a single run of a vertex pipeline, separate operation data for each view of the plurality of views; and render the plurality of views on the display.

25. The system of claim 24 , the three dimensional driver to cause the processing unit to render the operation data for each view of the plurality of views sequentially according to an interval period.

26. The system of claim 24 , the three dimensional driver to cause the processing unit to: clip the operation data for at least one view of the plurality of views; and tile the clipped operation data for the at least one view.